
import numpy as np
import pandas as pd
import seaborn as sns
import random
from matplotlib import pyplot as plt


data = pd.read_csv("../data/to_model/new_york_listings_2024_to_model.csv");
data.head()


data.shape

(16606, 22)


data.isnull().sum()

id                                0
name                              0
host_id                           0
host_name                         0
neighbourhood_group               0
neighbourhood                     0
latitude                          0
longitude                         0
room_type                         0
price                             0
minimum_nights                    0
number_of_reviews                 0
last_review                       0
reviews_per_month                 0
calculated_host_listings_count    0
availability_365                  0
number_of_reviews_ltm             0
license                           0
rating                            0
bedrooms                          0
beds                              0
baths                             0
dtype: int64


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16606 entries, 0 to 16605
Data columns (total 22 columns):
 #   Column                          Non-Null Count  Dtype  
---  ------                          --------------  -----  
 0   id                              16606 non-null  int64  
 1   name                            16606 non-null  object 
 2   host_id                         16606 non-null  int64  
 3   host_name                       16606 non-null  object 
 4   neighbourhood_group             16606 non-null  object 
 5   neighbourhood                   16606 non-null  object 
 6   latitude                        16606 non-null  float64
 7   longitude                       16606 non-null  float64
 8   room_type                       16606 non-null  object 
 9   price                           16606 non-null  float64
 10  minimum_nights                  16606 non-null  int64  
 11  number_of_reviews               16606 non-null  int64  
 12  last_review                     16606 non-null  object 
 13  reviews_per_month               16606 non-null  float64
 14  calculated_host_listings_count  16606 non-null  int64  
 15  availability_365                16606 non-null  int64  
 16  number_of_reviews_ltm           16606 non-null  int64  
 17  license                         16606 non-null  object 
 18  rating                          16606 non-null  object 
 19  bedrooms                        16606 non-null  object 
 20  beds                            16606 non-null  int64  
 21  baths                           16606 non-null  object 
dtypes: float64(4), int64(8), object(10)
memory usage: 2.8+ MB


import re

def contains_only_numbers_and_dots(s):
    pattern = r"^[0-9.]+$"
    return re.match(pattern, s.strip()) is not None


print(data["rating"][0])
contains_only_numbers_and_dots(data["rating"][0])

No rating

False


to_check = ["rating", "bedrooms", "baths"]
for i in to_check:
    series = data[i].loc[~data[i].apply(contains_only_numbers_and_dots)]
    print(series.value_counts())
    print("------------------------------")

No rating    2865
New           135
Name: rating, dtype: int64
------------------------------
Studio    1438
Name: bedrooms, dtype: int64
------------------------------
Not specified    12
Name: baths, dtype: int64
------------------------------


data.loc[data["baths"]=="Not specified"]["name"] # No możemy na spokojnie założyć teraz, że shared baths zaliczają sie do baths

67              Rental unit in Brooklyn · ★5.0 · 1 bedroom
166      Rental unit in New York · ★4.59 · Studio · 2 beds
4697     Rental unit in New York · ★4.17 · 1 bedroom · ...
6008                Townhouse in Brooklyn · ★4.87 · Studio
8626                    Home in Queens · ★4.74 · 1 bedroom
9829     Rental unit in Brooklyn · ★4.52 · 1 bedroom · ...
12497          Boutique hotel in New York · Studio · 1 bed
12921         Home in Brooklyn · ★4.96 · 1 bedroom · 1 bed
13012    Rental unit in New York · ★4.86 · 1 bedroom · ...
14569                   Hotel in New York · Studio · 1 bed
15425                  Rental unit in Brooklyn · 1 bedroom
15807          Rental unit in Brooklyn · 1 bedroom · 1 bed
Name: name, dtype: object


# Co jest zawarte w name (Można odpalić parę razy)
for i in range(20):
    print(data["name"][random.randint(0, data.shape[0])])

Home in Queens · ★4.0 · 1 bedroom · 1 bed · 1 shared bath
Townhouse in Queens · ★4.90 · 1 bedroom · 1 bed · 1 private bath
Rental unit in Brooklyn · ★4.77 · 2 bedrooms · 2 beds · 1 bath
Serviced apartment in Brooklyn · ★4.50 · 1 bedroom · 1 bed · 1 bath
Rental unit in Brooklyn · 1 bedroom · 1 bed · 1 shared bath
Rental unit in New York · ★4.50 · 1 bedroom · 1 bed · 2 shared baths
Rental unit in Brooklyn · ★4.85 · 1 bedroom · 1 bed · 1 shared bath
Rental unit in New York · ★4.75 · 1 bedroom · 1 bed · 1 bath
Rental unit in New York · ★4.86 · 1 bedroom · 1 bed · 1 bath
Rental unit in New York · ★4.61 · Studio · 1 bed · 1 bath
Rental unit in Brooklyn  · ★4.58 · 2 bedrooms · 2 beds · 1 bath
Rental unit in New York · ★4.43 · 1 bedroom · 1 bed · 3.5 shared baths
Rental unit in Queens · ★4.76 · 2 bedrooms · 4 beds · 1 bath
Boutique hotel in New York · ★4.45 · 1 bedroom · 1 bed · 1 shared bath
Rental unit in Brooklyn · ★4.70 · 1 bedroom · 2 beds · 1 bath
Rental unit in Brooklyn · ★4.67 · 1 bedroom · 1 bed · 1 shared bath
Home in Queens · ★3.80 · 1 bedroom · 1 bed · 2 shared baths
Rental unit in Brooklyn · 1 bedroom · 1 bed · 1 bath
Rental unit in New York · 1 bedroom · 2 beds · 1 bath
Rental unit in New York · ★4.38 · 1 bedroom · 1 bed · 1 bath


# przyjrzyjmy się host_id
data["host_id"].value_counts() # widać, ze jednak nie ma wiele firm dających na airbnb możliwość wynajęcia (czyli można wywalać potem)

51501835     107
162280872    103
61391963      96
107434423     81
19303369      72
            ... 
151692758      1
110346058      1
1388987        1
274605727      1
478704134      1
Name: host_id, Length: 10458, dtype: int64


data = data.drop(["id"], axis = 1)
data = data.drop(["name", "host_id", "host_name"], axis = 1)
data


data.describe()


data["license"].value_counts()  # Trzeba zbinować do jednej grupy poza no license i exemp

No License            14057
Exempt                 1702
OSE-STRREG-0000068       10
OSE-STRREG-0008664        6
OSE-STRREG-0000003        4
                      ...  
OSE-STRREG-0000152        1
OSE-STRREG-0000424        1
OSE-STRREG-0000956        1
OSE-STRREG-0000387        1
OSE-STRREG-0000341        1
Name: license, Length: 725, dtype: int64


def lic_mapper(a):
    if a == "No License" or a == "Exempt":
        return 0
    else:
        return 1


data["license"] = data["license"].map(lic_mapper)  # Jeśli ma licencję to 1, jeśli nie to 0
data["license"].value_counts()

0    15759
1      847
Name: license, dtype: int64


numerical = ["price", "minimum_nights", "number_of_reviews", "reviews_per_month", "calculated_host_listings_count", "availability_365", "number_of_reviews_ltm", "beds"]
hidden_numerical = ["rating", "bedrooms", "baths"]


# Odcięte 5% największych obserwacji (inaczej wykresy są tragiczne)
fig, axs = plt.subplots(6, 2, figsize = (12, 36))
axs = axs.flatten()

bins = [30, 20, 20, 20, 20, 20, 20, 20, 30, 20, 20]
# nasze numeryczne
for i, col in enumerate(numerical):
    series = data[col].loc[data[col] <= np.quantile(data[col], 0.95)]
    sns.histplot(x = series, ax=axs[i], color = "brown", kde = True, bins=bins[i]).set(title = col + " histogram")

# te ze stringami
for i, col in enumerate(hidden_numerical):
    series = data[col].loc[data[col].apply(contains_only_numbers_and_dots)].apply(float)
    series = series.loc[series <= np.quantile(series, 0.95)]
    sns.histplot(x = series, ax=axs[8+i], color = "brown", kde = True, bins = bins[i+8]).set(title = col + " histogram")
plt.tight_layout()
plt.show()


fig, axs = plt.subplots(6, 2, figsize = (12, 36))
axs = axs.flatten()

# nasze numeryczne
for i, col in enumerate(numerical):
    sns.boxplot(data = data, x = col, ax=axs[i], color = "brown").set(title = col + " boxplot")

# te ze stringami
for i, col in enumerate(hidden_numerical):
    series = data[col].loc[data[col].apply(contains_only_numbers_and_dots)].apply(float)
    sns.boxplot(x = series, ax=axs[8+i], color = "brown").set(title = col + " boxplot")
plt.tight_layout()
plt.show()


data.columns.difference(numerical)

Index(['baths', 'bedrooms', 'last_review', 'latitude', 'license', 'longitude',
       'neighbourhood', 'neighbourhood_group', 'rating', 'room_type'],
      dtype='object')


nonumerical = ['license', 'neighbourhood', 'neighbourhood_group', 'room_type']


# Funkcja pomocnicza do pokazywania procentów
def without_hue(ax, feature):
    total = len(feature)
    for p in ax.patches:
        percentage = '{:.1f}%'.format(100 * p.get_height()/total)
        x = p.get_x() + p.get_width() / 2 - 0.2
        y = p.get_y() + p.get_height()
        ax.annotate(percentage, (x, y), size = 12)


data["neighbourhood"].isin(data["neighbourhood"].value_counts()[data["neighbourhood"].value_counts()>30].index)

0         True
1         True
2         True
3         True
4         True
         ...  
16601     True
16602     True
16603    False
16604     True
16605     True
Name: neighbourhood, Length: 16606, dtype: bool


fig, axs = plt.subplots(2, 2, figsize = (14, 14))
axs = axs.flatten()

for i, col in enumerate(nonumerical):
    # Dla zmiennej neighbourhood wybieramy tylko te co mają nie mniej niż 200 występowań w ramce
    if col == "neighbourhood":
        series = data[col]
        counts = series.value_counts()
        series = series[series.isin(counts[counts>200].index)]
        fig = sns.countplot(x = series, ax = axs[i], color="brown", order=series.value_counts().index)
        fig.set_xticklabels(fig.get_xticklabels(), rotation=45, horizontalalignment='right')
        axs[i].set(title = "Countplot of " + col)
    else:
        sns.countplot(data = data, x = col, ax = axs[i], color="brown", order=data[col].value_counts().index).set(title = "Countplot of " + col)
        
        without_hue(axs[i], data[col])
    

plt.tight_layout()
plt.show()


# Zebrałem tu zmiany, które w następnych KM będzie można już od razu łatwiej implementować
# Trzeba pamiętac, że jeszcze był zmapowany license
def bath_mapper(a):
    if a == "Not specified":
        return 0
    else:
        return int(float(a))
def bedroom_mapper(a): # Uznałem, że posiadanie studio (czyli całe mieszkanie w jednym większym pokoju) to tak jakby była jedna sypialnia
    if a == "Studio":
        return 1
    else:
        return int(a)
def rating_mapper(a): # na razie tak może zostać
    if a == "New " or a == "No rating":
        return np.nan
    else:
        return float(a)
data["baths"] = data["baths"].map(bath_mapper)
data["bedrooms"] = data["bedrooms"].map(bedroom_mapper)
data["rating"] = data["rating"].map(rating_mapper)
data["last_review"] =  data["last_review"].map(np.datetime64) # Zmapowałem też date ostatniej opinii do przeznaczonego do tego typu
#data = data.drop(["name", "host_id", "host_name"], axis = 1) -> zrobilismy to wyzej + usunelismy id
data


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16606 entries, 0 to 16605
Data columns (total 18 columns):
 #   Column                          Non-Null Count  Dtype         
---  ------                          --------------  -----         
 0   neighbourhood_group             16606 non-null  object        
 1   neighbourhood                   16606 non-null  object        
 2   latitude                        16606 non-null  float64       
 3   longitude                       16606 non-null  float64       
 4   room_type                       16606 non-null  object        
 5   price                           16606 non-null  float64       
 6   minimum_nights                  16606 non-null  int64         
 7   number_of_reviews               16606 non-null  int64         
 8   last_review                     16606 non-null  datetime64[ns]
 9   reviews_per_month               16606 non-null  float64       
 10  calculated_host_listings_count  16606 non-null  int64         
 11  availability_365                16606 non-null  int64         
 12  number_of_reviews_ltm           16606 non-null  int64         
 13  license                         16606 non-null  int64         
 14  rating                          13606 non-null  float64       
 15  bedrooms                        16606 non-null  int64         
 16  beds                            16606 non-null  int64         
 17  baths                           16606 non-null  int64         
dtypes: datetime64[ns](1), float64(5), int64(9), object(3)
memory usage: 2.3+ MB


# Nic interesującego nie widać
plt.figure(figsize = (10, 10))
sns.heatmap(data.corr(), cmap = 'coolwarm', center = 0, vmax = 1, vmin = -1).set(title = "Correlation heatmap (whole df)")
plt.show()

C:\Users\barto\AppData\Local\Temp\ipykernel_4412\2243212398.py:3: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  sns.heatmap(data.corr(), cmap = 'coolwarm', center = 0, vmax = 1, vmin = -1).set(title = "Correlation heatmap (whole df)")


# Jeżeli usuniemy "nienormalne ceny" to mamy trochę lepszą wizję (ale dalej wsm nic)
plt.figure(figsize = (10, 10))
sns.heatmap(data[data["price"] <= np.quantile(data["price"], 0.95)].corr(), cmap = 'coolwarm', center = 0, vmax = 1, vmin = -1).set(title = "Correlation heatmap (without upper 5% prices)")
plt.show()

C:\Users\barto\AppData\Local\Temp\ipykernel_4412\2299295370.py:3: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  sns.heatmap(data[data["price"] <= np.quantile(data["price"], 0.95)].corr(), cmap = 'coolwarm', center = 0, vmax = 1, vmin = -1).set(title = "Correlation heatmap (without upper 5% prices)")


numerical = ['minimum_nights', 'number_of_reviews', 'reviews_per_month', 'calculated_host_listings_count', 'availability_365', 'number_of_reviews_ltm', 'license', 'rating','bedrooms', 'beds', 'baths']


np.quantile(data["price"], 0.95)

430.0


# Do plotowania usuwam 5% obserwacji górnych price (dalej będe się głównie tą ramką posługiwał)
price_df = data[data["price"] <= np.quantile(data["price"], 0.95)]


# No cóż punktów jest za dużo, aby sens miały scatter ploty, trzeba zrobić jakąś reprezentacje na heatmapach 
fig, axs = plt.subplots(6, 2, figsize = (10, 30))
axs = axs.flatten()
for i, col in enumerate(numerical):
    sns.scatterplot(data = price_df, y = "price", x = col, ax = axs[i], hue = "neighbourhood_group")
plt.tight_layout()
plt.show()


# Plot zapożyczony z poprzedniego projektu (W tym wypadku wpływ połączenia dwóch zmiennych numerycznych na cenę)
# Im ciemniejszy kwadrat tym wyższa jest średnia cena obserwacji danego kwadratu.
# Im bardziej w prawo lub im bardziej w górę tym wyższa wartość odpowiedniej zmiennej
# Wykres warto pobrać i tam sprawdzać jak wygląda na przybliżeniu
bins = 10
fig, axs = plt.subplots(10, 10, figsize = (50, 50))
fig.subplots_adjust(hspace = 0.4)

for i, col1 in enumerate(numerical):
    for j, col2 in enumerate(numerical):
        if j < i:
            df = pd.DataFrame({col1: pd.qcut(price_df[col1], q = bins, duplicates = "drop"),\
                  col2: pd.qcut(price_df[col2], q = bins, duplicates = "drop"),\
                  "price": price_df["price"].copy()})
            annot = df.groupby([col1, col2]).count().reset_index().pivot(index=col1, columns=col2, values="price").sort_index(ascending = False)
            df = df.groupby([col1, col2]).mean().reset_index().pivot(index=col1, columns=col2, values="price").sort_index(ascending = False)
            fig = sns.heatmap(df, cmap = sns.cm.rocket_r, ax = axs[i - 1][j], annot = annot, fmt='g')
            fig.tick_params(labelleft=False, left=False, labelbottom=False, bottom=False)
plt.tight_layout()
plt.show()


plt.figure(figsize = (10, 10))
sns.boxplot(data = price_df, y = "price", x = "beds", hue = "neighbourhood_group")
plt.show()


df = price_df[["price", "neighbourhood_group", 'room_type']].groupby(["neighbourhood_group", 'room_type']).mean().reset_index()

plt.figure(figsize = (10, 10))
ax = sns.barplot(data = df, y = "price", x = "neighbourhood_group", hue = "room_type")
ax.set(ylabel = "avg price")
plt.show()


df = price_df[["price", "neighbourhood_group", 'license']].groupby(["neighbourhood_group", 'license']).mean().reset_index()

plt.figure(figsize = (10, 10))
ax = sns.barplot(data = df, y = "price", x = "neighbourhood_group", hue = "license")
ax.set(ylabel = "avg price")
plt.show()


plt.figure(figsize = (10, 10))
ax = sns.boxplot(data = price_df, y = "price", x = pd.qcut(price_df["reviews_per_month"], q = 10))
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
plt.show()


plt.figure(figsize = (10, 10))
ax = sns.boxplot(data = price_df, y = "price", x = pd.cut(price_df["minimum_nights"], bins = 3))
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
plt.show()


plt.figure(figsize = (10, 10))
sns.boxplot(data = price_df, y = "rating", x = "neighbourhood_group")
plt.ylim([3.9,5.05])
plt.show()


plt.figure(figsize = (10, 10))
ax = sns.boxplot(data = price_df, y = "rating", x = pd.qcut(price_df["price"], q = 10))
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
plt.ylim([3.9,5.05])
plt.show()


plt.figure(figsize = (10, 10))
ax = sns.boxplot(data = price_df, y = "rating", x = pd.qcut(price_df["price"], q = 10), hue = "neighbourhood_group")
sns.move_legend(ax, 'lower right')
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
plt.ylim([3.9,5.05])
plt.show()


plt.figure(figsize = (10, 10))
ax = sns.boxplot(data = price_df, y = "rating", x = pd.qcut(price_df["reviews_per_month"], q = 10))
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
plt.ylim([3.9,5.05])
plt.show()


import plotly.express as px


fig = px.scatter_mapbox(data,
                    lat="latitude", lon="longitude", color="neighbourhood_group",
                    zoom=10, height=800)
fig.update_layout(mapbox_style="carto-positron")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()


fig = px.scatter_mapbox(data,
                    lat="latitude", lon="longitude", color="neighbourhood",
                    zoom=10, height=800)
fig.update_layout(mapbox_style="carto-positron")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.update_layout(showlegend = True)
fig.show()


# Problem w tym, że im większe skupisko ogłoszeń w danym miejsu tym jaśniejsza jest obserwacja, dlatego plot uznaję za bezsensowny
# Wystarczy pobawić się parametrem radius
fig = px.density_mapbox(price_df,
                    lat="latitude", lon="longitude", z="price", radius = 2,
                    zoom=10, height=800)
fig.update_layout(mapbox_style="carto-positron")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()


price_df.groupby("neighbourhood").count().reset_index()


# Pogrupujmy więc dane na te poddzielnice
# Wyliczymy średnią po wszystkich cechach (zmienne dotyczące położenia powinny wskazać środek tych poddzielnic)
df = price_df.groupby("neighbourhood").mean().reset_index()
df["counts"] = price_df.groupby("neighbourhood").count().reset_index()["latitude"]
fig = px.scatter_mapbox(df,
                    lat="latitude", lon="longitude",
                    size = "price", color = "rating", 
                    hover_name = "neighbourhood", hover_data = ["price", "rating", "counts"],
                    zoom=10, height=800, color_continuous_scale="bluered")
fig.update_layout(mapbox_style="carto-positron")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.update_layout(showlegend = False)
fig.show()

C:\Users\barto\AppData\Local\Temp\ipykernel_4412\3652456222.py:3: FutureWarning:

The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.


# Które dzielnice na topie? (mają największy rate opinii na miesiąc za poprzedni rok)
df = price_df.groupby("neighbourhood").median().reset_index()
df["counts"] = price_df.groupby("neighbourhood").count().reset_index()["latitude"]
fig = px.scatter_mapbox(df,
                    lat="latitude", lon="longitude",
                    size = "number_of_reviews_ltm", color = "rating", 
                    hover_name = "neighbourhood", hover_data = ["number_of_reviews_ltm", "rating", "counts"],
                    zoom=10, height=800, color_continuous_scale="bluered")
fig.update_layout(mapbox_style="carto-positron")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.update_layout(showlegend = False)
fig.show()

C:\Users\barto\AppData\Local\Temp\ipykernel_4412\4160348705.py:2: FutureWarning:

The default value of numeric_only in DataFrameGroupBy.median is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.

	id	name	host_id	host_name	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	...	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license	rating	bedrooms	beds	baths
0	718037328155265207	Rental unit in Queens · 5 bedrooms · 8 beds · ...	204539	Mark	Queens	Ridgewood	40.70262	-73.89800	Entire home/apt	471.0	...	2022-11-03	0.07	9	365	0	No License	No rating	5	8	2
1	5536638	Rental unit in Brooklyn · ★4.60 · 2 bedrooms ·...	28709982	Sidiq	Brooklyn	Williamsburg	40.72027	-73.95513	Entire home/apt	225.0	...	2023-09-13	0.49	5	90	7	No License	4.60	2	2	1
2	4605840	Rental unit in Brooklyn · ★4.93 · 1 bedroom · ...	23788242	Suzanne	Brooklyn	Bedford-Stuyvesant	40.68670	-73.94856	Private room	80.0	...	2023-11-17	1.00	2	363	12	No License	4.93	1	1	1
3	594240338554500815	Rental unit in New York · 1 bedroom · 1 bed · ...	384559808	Best Inns USA	Manhattan	East Village	40.73221	-73.98689	Entire home/apt	83.0	...	2023-08-11	0.12	30	106	1	No License	No rating	1	1	1
4	26785	Rental unit in Brooklyn · ★4.93 · 1 bedroom · ...	42273	Dani	Brooklyn	South Slope	40.66860	-73.98723	Entire home/apt	90.0	...	2022-05-31	2.90	3	188	0	No License	4.93	1	1	1

	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license	rating	bedrooms	beds	baths
0	Queens	Ridgewood	40.702620	-73.898000	Entire home/apt	471.0	30	1	2022-11-03	0.07	9	365	0	No License	No rating	5	8	2
1	Brooklyn	Williamsburg	40.720270	-73.955130	Entire home/apt	225.0	30	52	2023-09-13	0.49	5	90	7	No License	4.60	2	2	1
2	Brooklyn	Bedford-Stuyvesant	40.686700	-73.948560	Private room	80.0	30	101	2023-11-17	1.00	2	363	12	No License	4.93	1	1	1
3	Manhattan	East Village	40.732210	-73.986890	Entire home/apt	83.0	30	2	2023-08-11	0.12	30	106	1	No License	No rating	1	1	1
4	Brooklyn	South Slope	40.668600	-73.987230	Entire home/apt	90.0	30	479	2022-05-31	2.90	3	188	0	No License	4.93	1	1	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
16601	Brooklyn	Bedford-Stuyvesant	40.686001	-73.943693	Entire home/apt	135.0	30	15	2023-01-10	0.97	1	262	1	No License	4.87	3	3	1
16602	Queens	Corona	40.745100	-73.864880	Private room	68.0	30	16	2023-10-16	2.68	2	180	16	No License	4.69	1	1	1
16603	Bronx	Allerton	40.867770	-73.860180	Entire home/apt	100.0	30	30	2023-10-07	2.21	5	365	24	No License	4.73	1	1	1
16604	Manhattan	Harlem	40.830791	-73.949509	Private room	50.0	30	19	2023-12-10	0.21	4	42	1	No License	4.84	1	1	1.5
16605	Manhattan	Midtown	40.762250	-73.978280	Entire home/apt	130.0	30	2	2023-06-01	0.20	5	365	2	No License	No rating	1	1	1

	latitude	longitude	price	minimum_nights	number_of_reviews	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	beds
count	16606.000000	16606.000000	16606.000000	16606.000000	16606.000000	16606.000000	16606.000000	16606.000000	16606.000000	16606.00000
mean	40.726740	-73.939112	190.328074	28.619716	42.664158	1.256612	18.554077	205.954113	10.804649	1.72799
std	0.060366	0.061366	1134.545935	35.219921	74.116856	1.903427	69.620276	135.066607	21.126468	1.22619
min	40.500314	-74.249840	10.000000	1.000000	1.000000	0.010000	1.000000	0.000000	0.000000	1.00000
25%	40.684119	-73.980840	80.000000	30.000000	4.000000	0.210000	1.000000	87.000000	1.000000	1.00000
50%	40.722935	-73.949650	125.000000	30.000000	14.000000	0.650000	2.000000	214.000000	3.000000	1.00000
75%	40.763025	-73.917362	199.000000	30.000000	49.000000	1.800000	5.000000	354.000000	15.000000	2.00000
max	40.911147	-73.713650	100000.000000	1250.000000	1865.000000	75.490000	713.000000	365.000000	1075.000000	42.00000

	neighbourhood_group	neighbourhood	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license	rating	bedrooms	beds	baths
0	Queens	Ridgewood	40.702620	-73.898000	Entire home/apt	471.0	30	1	2022-11-03	0.07	9	365	0	0	NaN	5	8	2
1	Brooklyn	Williamsburg	40.720270	-73.955130	Entire home/apt	225.0	30	52	2023-09-13	0.49	5	90	7	0	4.60	2	2	1
2	Brooklyn	Bedford-Stuyvesant	40.686700	-73.948560	Private room	80.0	30	101	2023-11-17	1.00	2	363	12	0	4.93	1	1	1
3	Manhattan	East Village	40.732210	-73.986890	Entire home/apt	83.0	30	2	2023-08-11	0.12	30	106	1	0	NaN	1	1	1
4	Brooklyn	South Slope	40.668600	-73.987230	Entire home/apt	90.0	30	479	2022-05-31	2.90	3	188	0	0	4.93	1	1	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
16601	Brooklyn	Bedford-Stuyvesant	40.686001	-73.943693	Entire home/apt	135.0	30	15	2023-01-10	0.97	1	262	1	0	4.87	3	3	1
16602	Queens	Corona	40.745100	-73.864880	Private room	68.0	30	16	2023-10-16	2.68	2	180	16	0	4.69	1	1	1
16603	Bronx	Allerton	40.867770	-73.860180	Entire home/apt	100.0	30	30	2023-10-07	2.21	5	365	24	0	4.73	1	1	1
16604	Manhattan	Harlem	40.830791	-73.949509	Private room	50.0	30	19	2023-12-10	0.21	4	42	1	0	4.84	1	1	1
16605	Manhattan	Midtown	40.762250	-73.978280	Entire home/apt	130.0	30	2	2023-06-01	0.20	5	365	2	0	NaN	1	1	1

EDA¶

1. wczytanie danych i bibliotek¶

sprawdzenie podsatwowych informacji o ramce¶

wartości Null w ramce¶

informacje o kolumnach¶

wstepne wnioski o tym ktore kolumny warto zostawić¶

przyjrzyjmy się wartościom w kolumnach¶

Przyjrzyjmy sie kolumnie license - binujemy ją na 0 i 1¶

2. Pierwsze wykresy¶

2.1 Numeryczne¶

Outliery¶

2.2 Nienumerycze¶

2.3 Zmiany po plottowaniu w ramce¶

2.4 Heatmapa po wyczyszczeniu ramki¶

2.5 Wpływ zmiennych na cenę¶

Wpływ dzielnicy na cenę¶

wplyw typu pokoju na cene¶

Wpływ tego czy lokum ma licencje na cenę¶

Wpływ ilości opini na cenę¶

Wpływ liosci spedzonych nocy na cenę¶

2.6 Wpływ zmiennych na rating¶

dzielnica¶

cena¶

cena i dzielnica¶

ilość opinii¶

3. Mapy¶

	neighbourhood	neighbourhood_group	latitude	longitude	room_type	price	minimum_nights	number_of_reviews	last_review	reviews_per_month	calculated_host_listings_count	availability_365	number_of_reviews_ltm	license	rating	bedrooms	beds	baths
0	Allerton	28	28	28	28	28	28	28	28	28	28	28	28	28	26	28	28	28
1	Arden Heights	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4
2	Arrochar	11	11	11	11	11	11	11	11	11	11	11	11	11	8	11	11	11
3	Arverne	48	48	48	48	48	48	48	48	48	48	48	48	48	43	48	48	48
4	Astoria	274	274	274	274	274	274	274	274	274	274	274	274	274	244	274	274	274
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
214	Windsor Terrace	41	41	41	41	41	41	41	41	41	41	41	41	41	35	41	41	41
215	Woodhaven	55	55	55	55	55	55	55	55	55	55	55	55	55	45	55	55	55
216	Woodlawn	6	6	6	6	6	6	6	6	6	6	6	6	6	5	6	6	6
217	Woodrow	3	3	3	3	3	3	3	3	3	3	3	3	3	1	3	3	3
218	Woodside	141	141	141	141	141	141	141	141	141	141	141	141	141	105	141	141	141